arXiv:2609.36932v1 Announce Type: new Abstract: Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy…
Tag: AI
SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents
arXiv:2609.36939v1 Announce Type: new Abstract: GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces.…
STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking
arXiv:2609.36900v1 Announce Type: new Abstract: Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive…
Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation
arXiv:2609.36888v1 Announce Type: new Abstract: Mixed human-LLM documents require locating authorship transitions from detector scores whose reliability…
HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RL
arXiv:2609.36896v1 Announce Type: new Abstract: Recent advances in generative planning have made trajectory inpainting a promising approach to offline…
PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval
arXiv:2609.36923v1 Announce Type: new Abstract: Existing reactive Graphical User Interface (GUI) agents often fail in long-horizon, dynamic scenarios,…
Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents
arXiv:2609.36892v1 Announce Type: new Abstract: As the capabilities of large language models (LLMs) continue to advance, increasing attention is turning…
State Trace Rationale As Auxiliary Task in Reinforcement Learning
arXiv:2609.36867v1 Announce Type: new Abstract: We propose STRAT, an auxiliary task that trains deep reinforcement learning (RL) agents to predict a short…
IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence
arXiv:2609.36860v1 Announce Type: new Abstract: We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference.…
WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
arXiv:2609.36887v1 Announce Type: new Abstract: Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable…
